Search Results (41)

Dissolved gas analysis remains the most widely utilized non-intrusive diagnostic method for detecting incipient faults in insulating liquid-immersed transformers. Despite their prevalence, conventional ratio-based methods often suffer from ambiguity and limited potential for automation applicrations. To address these limitations, this study proposes a unified multiclass classification model that integrates traditional gas ratio features with supervised machine learning algorithms to enhance fault diagnosis accuracy. The performance of six machine learning classifiers was systematically evaluated using training and testing data generated through four widely recognized gas ratio schemes. Grid search optimization was employed to fine-tune the hyperparameters of each model, while model evaluation was conducted using 10-fold cross-validation and six performance metrics. Across all the diagnostic approaches, ensemble models, namely random forest, XGBoost, and LightGBM, consistently outperformed non-ensemble models. Notably, random forest and LightGBM classifiers demonstrated the most robust and superior performance across all schemes, achieving accuracy, precision, recall, and F1 scores between 0.99 and 1, along with Matthew correlation coefficient values exceeding 0.98 in all cases. This robustness suggests that ensemble models are effective at capturing complex decision boundaries and relationships among gas ratio features. Furthermore, beyond numerical classification, the integration of physicochemical and dielectric properties in this study revealed degradation signatures that strongly correlate with thermal fault indicators. Particularly, the CIGRÉ-based classification using a random forest classifier demonstrated high sensitivity in detecting thermally stressed units, corroborating trends observed in chemical deterioration parameters such as interfacial tension and CO₂/CO ratios. Access to over 80 years of operational data provides a rare and invaluable perspective on the long-term performance and degradation of power equipment. This extended dataset enables a more accurate assessment of ageing trends, enhances the reliability of predictive maintenance models, and supports informed decision-making for asset management in legacy power systems. Full article

Autism Spectrum Disorder (ASD) poses significant challenges in diagnosis due to its diverse symptomatology and the complexity of early detection. Atypical gait and gesture patterns, prominent behavioural markers of ASD, hold immense potential for facilitating early intervention and optimising treatment outcomes. These patterns can be efficiently and non-intrusively captured using modern computational techniques, making them valuable for ASD recognition. Various types of research have been conducted to detect ASD through deep learning, including facial feature analysis, eye gaze analysis, and movement and gesture analysis. In this study, we optimise a dual-stream architecture that combines image classification and skeleton recognition models to analyse video data for body motion analysis. The first stream processes Skepxels—spatial representations derived from skeleton data—using ConvNeXt-Base, a robust image recognition model that efficiently captures aggregated spatial embeddings. The second stream encodes angular features, embedding relative joint angles into the skeleton sequence and extracting spatiotemporal dynamics using Multi-Scale Graph 3D Convolutional Network(MSG3D), a combination of Graph Convolutional Networks (GCNs) and Temporal Convolutional Networks (TCNs). We replace the ViT model from the original architecture with ConvNeXt-Base to evaluate the efficacy of CNN-based models in capturing gesture-related features for ASD detection. Additionally, we experimented with a Stack Transformer in the second stream instead of MSG3D but found it to result in lower performance accuracy, thus highlighting the importance of GCN-based models for motion analysis. The integration of these two streams ensures comprehensive feature extraction, capturing both global and detailed motion patterns. A pairwise Euclidean distance loss is employed during training to enhance the consistency and robustness of feature representations. The results from our experiments demonstrate that the two-stream approach, combining ConvNeXt-Base and MSG3D, offers a promising method for effective autism detection. This approach not only enhances accuracy but also contributes valuable insights into optimising deep learning models for gesture-based recognition. By integrating image classification and skeleton recognition, we can better capture both global and detailed motion patterns, which are crucial for improving early ASD diagnosis and intervention strategies. Full article

The increasing prevalence of IoT technology in smart homes has significantly enhanced convenience but also introduced new security and safety challenges. Traditional security solutions, reliant on sequences of IoT-generated event data (e.g., notifications of device status changes and sensor readings), are vulnerable to cyberattacks, such as message forgery and interception and delaying attacks, and fail to monitor non-smart devices. Moreover, fragmented smart home ecosystems require vendor cooperation or system modifications for comprehensive monitoring, limiting the practicality of the existing approaches. To address these issues, we propose IoTBystander, a non-intrusive dual-channel smart home security monitoring framework that utilizes two ubiquitous platform-agnostic signals, i.e., audio and network, to monitor user and device activities. We introduce a novel dual-channel aggregation mechanism that integrates insights from both channels and cross-verifies the integrity of monitoring results. This approach expands the monitoring scope to include non-smart devices and provides richer context for anomaly detection, failure diagnosis, and configuration debugging. Empirical evaluations on a real-world testbed with nine smart and eleven non-smart devices demonstrate the high accuracy of IoTBystander in event recognition: 92.86% for recognizing events of smart devices, 95.09% for non-smart devices, and 94.27% for all devices. A case study on five anomaly scenarios further shows significant improvements in anomaly detection performance by combining the strengths of both channels. Full article

The early diagnosis of Alzheimer’s disease remains an unmet medical need due to the cost and invasiveness of current methods. Early detection would ensure a higher quality of life for patients, enabling timely and suitable treatment. We investigate microwave sensing for low-cost, non-intrusive early detection and assessment of Alzheimer’s disease. This study is based on the emerging evidence that the electromagnetic properties of cerebrospinal fluid are affected by abnormal concentrations of proteins recognized as early-stage biomarkers. We design a conformal six-element antenna array placed on the upper portion of the head, operating in the 500 MHz to 6.5 GHz band. It measures scattering response due to changes in the dielectric properties of intracranial cerebrospinal fluid. A multi-layer perceptron network extracts the diagnostic information. Data classification consists of two steps: binary classification to identify the disease presence and multi-class classification to evaluate its stage. The algorithm is trained and validated through controlled experiments mimicking various pathological severities with an anthropomorphic multi-tissue head phantom. Results support the feasibility of the proposed method using only amplitude data and lay the foundation for more extensive studies on microwave sensing for early Alzheimer’s detection. Full article

Lung cancer still represents one of the main causes of cancer-related mortality, highlighting the necessity for precise, effective, and minimally intrusive diagnostic methods. This research presents an innovative approach to classifying lung lesions using Doppler ultrasound imagery combined with a feed-forward neural network (FNN). This study integrates Doppler mode ultrasound vascularization features—blood vessel area, tortuosity index, and orientation—into an FNN to classify lung lesions as benign or malignant. A dataset of 565 Doppler ultrasound pictures was extended using augmentation techniques to enhance robustness, yielding a training dataset of 3390 images. The FNN architecture was trained utilizing the Levenberg–Marquardt algorithm, achieving a classification accuracy of 98%, demonstrating its potential as a diagnostic aid. The results indicate that integrating all three vascularization factors significantly improves diagnosis accuracy compared with individual modules. This method offers a non-invasive and cost-effective complementary tool to conventional techniques such as CT scans, with the potential to improve early detection and treatment planning for lung cancer patients. Full article

Drowsiness while driving is a major factor contributing to traffic accidents, resulting in reduced cognitive performance and increased risk. This article gives a complete analysis of a real-time, non-intrusive sleepiness detection system based on convolutional neural networks (CNNs). The device analyses video data recorded from an in-vehicle camera to monitor drivers’ facial expressions and detect fatigue indicators such as yawning and eye states. The system is built on a strong architecture and was trained using a diversified dataset under varying lighting circumstances and facial angles. It uses Haar cascade classifiers for facial area extraction and advanced image processing algorithms for fatigue diagnosis. The results demonstrate that the system obtained a 96.54% testing accuracy, demonstrating the efficiency of using behavioural indicators such as yawning frequency and eye state detection to improve performance. The findings show that CNN-based architectures can address major public safety concerns, such as minimizing accidents caused by drowsy driving. This study not only emphasizes the need of deep learning in establishing dependable and practical driver monitoring systems, but it also lays the groundwork for future improvements, such as the incorporation of new behavioural and physiological measurements. The suggested solution is a big step towards increasing road safety and reducing the risks associated with driver weariness. Full article

Anemia diagnosis is crucial for pediatric patients due to its impact on growth and development. Traditional methods, like blood tests, are effective but pose challenges, such as discomfort, infection risk, and frequent monitoring difficulties, underscoring the need for non-intrusive diagnostic methods. In light of this, this study proposes a novel method that combines image processing with learning-driven data representation and model behavior for non-intrusive anemia diagnosis in pediatric patients. The contributions of this study are threefold. First, it uses an image-processing pipeline to extract 181 features from 13 categories, with a feature-selection process identifying the most crucial data for learning. Second, a deep multilayered network based on long short-term memory (LSTM) is utilized to train a model for classifying images into anemic and non-anemic cases, where hyperparameters are optimized using Bayesian approaches. Third, the trained LSTM model is integrated as a layer into a learning model developed based on recurrent expansion rules, forming a part of a new deep network called a recurrent expansion network (RexNet). RexNet is designed to learn data representations akin to traditional deep-learning methods while also understanding the interaction between dependent and independent variables. The proposed approach is applied to three public datasets, namely conjunctival eye images, palmar images, and fingernail images of children aged up to 6 years. RexNet achieves an overall evaluation of 99.83 ± 0.02% across all classification metrics, demonstrating significant improvements in diagnostic results and generalization compared to LSTM networks and existing methods. This highlights RexNet’s potential as a promising alternative to traditional blood-based methods for non-intrusive anemia diagnosis. Full article

Lung cancer is responsible for the death of over a million people worldwide every year. With its high mortality rate and exponentially growing number of new cases, lung cancer is a major threat to public health. The high mortality and poor survival rates of lung cancer patients can be attributed to its stealth progression and late diagnosis. For a long time, intrusive tissue biopsy has been considered the gold standard for lung cancer diagnosis and subtyping; however, the intrinsic limitations of tissue biopsy cannot be overlooked. In addition to being invasive and costly, it also suffers from limitations in sensitivity and specificity, is not suitable for repeated sampling, provides restricted information about the tumor and its molecular landscape, and is inaccessible in several cases. To cope with this, advancements in diagnostic technologies, such as liquid biopsy, have shown great prospects. Liquid biopsy is an innovative non-invasive approach in which cancer-related components called biomarkers are detected in body fluids, such as blood, urine, saliva and others. It offers a less invasive alternative with the potential for applications such as routine screening, predicting treatment outcomes, evaluating treatment effectiveness, detecting residual disease, or disease recurrence. A large number of research articles have indicated extracellular vesicles (EVs) as ideal biomarkers for liquid biopsy. EVs are a heterogeneous collection of membranous nanoparticles with diverse sizes, contents, and surface markers. EVs play a critical role in pathophysiological states and have gained prominence as diagnostic and prognostic biomarkers for multiple diseases, including lung cancer. In this review, we provide a detailed overview of the potential of EV-based liquid biopsy for lung cancer. Moreover, it highlights the strengths and weaknesses of various contemporary techniques for EV isolation and analysis in addition to the challenges that need to be addressed to ensure the widespread clinical application of EV-based liquid biopsies for lung cancer. In summary, EV-based liquid biopsies present interesting opportunities for the development of novel diagnostic and prognostic platforms for lung cancer, one of the most abundant cancers responsible for millions of cancer-related deaths worldwide. Full article

Imbalance classification is common in scenarios like fault diagnosis, intrusion detection, and medical diagnosis, where obtaining abnormal data is difficult. This article addresses a one-class problem, implementing and refining the One-Class Nearest-Neighbor (OCNN) algorithm. The original inter-quartile range mechanism is replaced with the K-means with outlier removal (KMOR) algorithm for efficient outlier identification in the target class. Parameters are optimized by treating these outliers as non-target-class samples. A new algorithm, the Location-based Nearest-Neighbor (LBNN) algorithm, clusters one-class training data using KMOR and calculates the farthest distance and percentile for each test data point to determine if it belongs to the target class. Experiments cover parameter studies, validation on eight standard imbalanced datasets from KEEL, and three applications on real medical imbalanced datasets. Results show superior performance in precision, recall, and G-means compared to traditional classification models, making it effective for handling imbalanced data challenges. Full article

In the realm of space exploration, solid rocket motors (SRMs) play a pivotal role due to their reliability and high thrust-to-weight ratio. Serving as boosters in space launch vehicles and employed in military systems, and other critical & emerging applications, SRMs’ structural integrity monitoring, is of paramount importance. Traditional maintenance approaches often prove inefficient, leading to either unnecessary interventions or unexpected failures. Condition-based maintenance (CBM) emerges as a transformative strategy, incorporating advanced sensing technologies and predictive analytics. By continuously monitoring crucial parameters such as temperature, pressure, and strain, CBM enables real-time analysis, ensuring timely intervention upon detecting anomalies, thereby optimizing SRM lifecycle management. This paper critically evaluates conventional SRM health diagnosis methods and explores emerging sensing technologies. Photonic sensors and fiber-optic sensors, in particular, demonstrate exceptional promise. Their enhanced sensitivity and broad measurement range allow precise monitoring of temperature, strain, pressure, and vibration, capturing subtle changes indicative of degradation or potential failures. These sensors enable comprehensive, non-intrusive monitoring of multiple SRM locations simultaneously. Integrated with data analytics, these sensors empower predictive analysis, facilitating SRM behavior prediction and optimal maintenance planning. Ultimately, CBM, bolstered by advanced photonic sensors, promises enhanced operational availability, reduced costs, improved safety, and efficient resource allocation in SRM applications. Full article

As mental health (MH) disorders become increasingly prevalent, their multifaceted symptoms and comorbidities with other conditions introduce complexity to diagnosis, posing a risk of underdiagnosis. While machine learning (ML) has been explored to mitigate these challenges, we hypothesized that multiple data modalities support more comprehensive detection and that non-intrusive collection approaches better capture natural behaviors. To understand the current trends, we systematically reviewed 184 studies to assess feature extraction, feature fusion, and ML methodologies applied to detect MH disorders from passively sensed multimodal data, including audio and video recordings, social media, smartphones, and wearable devices. Our findings revealed varying correlations of modality-specific features in individualized contexts, potentially influenced by demographics and personalities. We also observed the growing adoption of neural network architectures for model-level fusion and as ML algorithms, which have demonstrated promising efficacy in handling high-dimensional features while modeling within and cross-modality relationships. This work provides future researchers with a clear taxonomy of methodological approaches to multimodal detection of MH disorders to inspire future methodological advancements. The comprehensive analysis also guides and supports future researchers in making informed decisions to select an optimal data source that aligns with specific use cases based on the MH disorder of interest. Full article

Background: Sleep is a critical factor in maintaining good health, and its impact on various diseases has been recognized by scientists. Understanding sleep patterns and quality is crucial for investigating sleep-related disorders and their potential links to health conditions. The development of non-intrusive and contactless methods for analyzing sleep data is essential for accurate diagnosis and treatment. Methods: A novel system called the sleep visual analyzer (VSleep) was designed to analyze sleep movements and generate reports based on changes in body position angles. The system utilized camera data without requiring any physical contact with the body. A Python graphical user interface (GUI) section was developed to analyze body movements during sleep and present the data in an Excel format. To evaluate the effectiveness of the VSleep system, a case study was conducted. The participants’ movements during daytime naps were recorded. The study also examined the impact of different types of news (positive, neutral, and negative) on sleep patterns. Results: The system successfully detected and recorded various angles formed by participants’ bodies, providing detailed information about their sleep patterns. The results revealed distinct effects based on the news category, highlighting the potential impact of external factors on sleep quality and behaviors. Conclusions: The sleep visual analyzer (VSleep) demonstrated its efficacy in analyzing sleep-related data without the need for accessories. The VSleep system holds great potential for diagnosing and investigating sleep-related disorders. The proposed system is affordable, easy to use, portable, and a mobile application can be developed to perform the experiment and prepare the results. Full article

The study focuses on Alzheimer’s and dementia detection using machine learning, acknowledging their impact on cognitive health beyond normal aging. Data markers, rather than biomarkers, are preferred for diagnosis, allowing machine learning to play a role. The objective is to design and test a model for early dementia detection using lifestyle data from the National Health and Ageing Trends Study (NHATS). This could aid in flagging high-risk individuals and understanding aging-related parameter changes. Using NHATS data from 5000 individuals aged 60+, encompassing 1288 parameters over a decade, the study shortlists parameters relevant to dementia. Artificial neural networks and random forest techniques are employed to build a model that identifies key dementia-related parameters. Temporal analysis reveals features that exhibit declining social interactions, quality of life, and increased depression as individuals age. Results show the random forest model achieving an accuracy of 80% for dementia risk prediction, with precision, recall, and F1-score values of 0.76, 1, and 0.86, respectively. Temporal analysis offers insights into aging trends and elderly citizens’ lifestyles, using daily activities as parameters. The study concludes that NHATS data analysed using machine learning techniques aids in understanding aging trends and that machine learning models based on identified parameters can non-intrusively assist in clinical dementia diagnosis and trend-based detection. Full article

Schizophrenia is a chronic and severe mental disorder that affects individuals in various ways, particularly in their ability to perceive, process, and respond to stimuli. This condition has a significant impact on a considerable number of individuals. Consequently, the study, analysis, and characterization of this pathology are of paramount importance. Electroencephalography (EEG) is frequently utilized in the diagnostic assessment of various brain disorders due to its non-intrusiveness, excellent resolution and ease of placement. However, the manual analysis of electroencephalogram (EEG) recordings can be a complex and time-consuming task for healthcare professionals. Therefore, the automated analysis of EEG recordings can help alleviate the burden on doctors and provide valuable insights to support clinical diagnosis. Many studies are working along these lines. In this research paper, the authors propose a machine learning (ML) method based on the eXtreme Gradient Boosting (XGB) algorithm for analyzing EEG signals. The study compares the performance of the proposed XGB-based approach with four other supervised ML systems. According to the results, the proposed XGB-based method demonstrates superior performance, with an AUC value of 0.94 and an accuracy value of 0.94, surpassing the other compared methods. The implemented system exhibits high accuracy and robustness in accurately classifying schizophrenia patients based on EEG recordings. This method holds the potential to be implemented as a valuable complementary tool for clinical use in hospitals, supporting clinicians in their clinical diagnosis of schizophrenia. Full article

Detecting human head movement during sleep is important as it can help doctors to assess many physical or mental health problems, such as infantile eczema, calcium deficiency, insomnia, anxiety disorder, and even Parkinson’s disease, and provide useful clues for accurate diagnosis. To obtain the information of head movement during sleep, current solutions either use a camera or require the user to wear intrusive sensors to collect the image or motion data. However, the vision-based schemes rely on light conditions and raise privacy concerns. Many people, including the elderly and infants, may be reluctant to wear wearable devices during sleep. In this paper, we propose Wi-Senser, a nonintrusive and contactless smart monitoring system for detecting head movement during sleep. Wi-Senser directly reuses the existing WiFi infrastructure and exploits the fine-grained channel state information (CSI) of WiFi signals to capture the minute human head movement during sleep without attaching any sensors to the human body. Specifically, we constructed a filtering channel including a Hampel filter, wavelet filter, and mean filter to remove outliers and noises. We propose a new metric of carrier sensitivity to select an optimal subcarrier for recording the change in targeted body movement from 30 candidate subcarriers. Finally, we designed a peak-finding algorithm to capture the real peak set recording the change in human head movement. We designed and implemented Wi-Senser with just one commercial off-the-shelf (COTS) router and one laptop equipped with an Intel 5300 network interface card (NIC). We evaluated the performance of Wi-Senser with 10 volunteers (6 adults and 4 children). Extensive experiments demonstrate that Wi-Senser can achieve 97.95% accuracy for monitoring head movement during sleep. Wi-Senser provides a new solution for achieving noninvasive, continuous, and accurate detection of minute human movement without any additional cost. Full article